Rethinking SSDs?

NAND Flash's SSD Vision: Wholesale replacement of HDDs by SSDs in the huge market for PCs and laptops archival storage has gleamed in the eyes of NAND Flash makers ever since Apple kicked the microHDD out of the iPod Mini and made it a SSD/Flash based iPod nano in 2005. Maybe it occurred even before that, but it had not caught the popular fancy, or seemed within reach until it happened with the 4GB or 8GB MP3 players from Apple. Almost instantly, flash makers set their sights on displacing, over time, huge swaths of the market for HDDs in laptops...250M units a year, variously averaging 160GB-400GB each.

Over the timeframe of 2004 through the end of 2008, NAND Flash came down in price nearly 100x. Most NAND flash applications fell easily under the sway of MLC NAND, with its lower costs (prices), which were gladly accepted in exchange for its reduced performance and endurance (specs). However, much of the SSD space claimed to need, and depend on, SLC NAND for sufficient specmanship and performance. Still, as in all applications, MLC was steadily improved in its performance, and 'patched MLC' NAND, with advanced software and sometimes hardware improvements, eventually became acceptable for many or most HDD replacements.

However, the latest data and analysis from Digitimes [24 Jun 2009: SSD penetration in PC market remains low, Members only] indicates that laptops with SSDs, in 2009, still will be only about 1.5% of total laptop shipments (though Gartner ramps it up to 20% in 2010, but we shall see), and the price of SSDs is most often given as the critical shortcoming amid a host of technical benefits for SSDs, real and perceived: lower operating power, faster reads and writes (easy random accesses), and G-force ruggedness.

But, all performance issues aside (which are now 'no news'), it is the SSD pricing that is keeping them away from wholesale adoption in the compute space.

While some technical criticisms remain, the most significant limitation is cost or price: Corsair's newest 128GB SSD carries a retail price of $414, against a HDD of similar capacity, for which it's easy to find 160GB HDDs for under $100 (and as low as $35). The Corsair SSD line-up has better performance, to be sure: 240MB/sec reads and 170MB/sec writes. But it will probably take a while for the consumer to understand what that means to him in terms of improved workload processing, impatiently waiting for data, and productivity.

Today, one has to ask what this extra $300 might be worth to the user, or how large that class of users who value SSD over HDD, at +$300, might be. Or, is this the BEST place to spend an incremental $300 on a system that costs about $1250 +/- $250, given other software and performance boosters that are available. Adding +25% or so in price is, yes, a significant price uplift for SSD's 'turbo speed' compared to HDD. For sure, some users and applications REALLY need the increased storage speed that SSDs offer. But, most, we think, will likely bide their time and wait for the eventual improvement in the "SSD Value Proposition".

Even in the low-capacity drive space, 32-64GB, SSDs are the high-priced spread, by a wide margin. So unless SSD makers can sell the 'consumer benefits' of their product better, the market will be thin for a while. The eternal hope of SSD and NAND Flash makers, that future NAND price reductions will bring HDDs within striking distance of NAND-based SSDs, is offset by the persistent trend in PC/Laptop applications and use, to 'demand' larger and larger capacity disk HDDs...by up to 20%/year in the high volume PC and laptop segments...today 160GB or 250GB, and tomorrow 200-300GB. Overtaking the HDD-in-laptop capacity trend line is a tall order for SSDs: the larger the drive, the more cost advantage HDDs have.

Put that on top of the fact that what we have seen 'recently' (the past five years) in NAND price reductions is probably an unsustainable trend, and will have to be slowed down due to technical barriers and the current lack of profitability among NAND makers. Nearly exhausted by running so fast for five years, and sinking so much money into technology and fabs, they have barely come close to the lagging end of HDDs, as they find their capital nearly spent.

What we see today in the SSD space, is early adopters, those who REALLY value lower power and better R/W performance of NAND Flash. But so far the price is steep, and a general overtaking of the broader HDD market, at least with pure SSDs, is not in the offing unless something changes pretty dramatically, no matter what the flash price curves look like.

If one looks at the average prices of either laptops or desktops in the past 10-15 years, too, it is down-down-down. There is huge resistance to increasing prices for the "Typical System", no matter what the performance, or what the performance improvement is. Sure, there are high-end systems, more costly and with more performance. There is always a spread of users and applications, from ultra-cheap and performance limited, to ultra-expensive and powerful. But it is the Middle Class where the high volume is. Unless SSDs can crack that nut, they will forever be elite specialty customer plays.

Changing mindsets: So, with the experience of about five years of talking, designing, building and selling SSDs, we collectively have a greater understanding of what might lie ahead, and/or how apparent barriers to SSD adoption might be overcome. For one, our concept of the "Computer-HDD" market, and its applications, has to be de-homogenized and scrutinized several levels deeper than viewing it as some monolithic construct. There are large groups within the market which will embrace SSDs, while others are too price-sensitive to do so. If corporate IT managers can find a way to keep employees from filling up their computers with home movies, vacation photos and other large GB applications, maybe a desktop computer with a 32GB SSD is plenty for most workers' legitimate business needs. This, however, is contrary to the PC trend of the past 30 years, to 'client empowerment'. But, it is not impossible.

Consumers can ask, "What is faster seek time worth, really?" Designers can ask, "Are there interface conventions and legacies that could be circumvented or overcome with some kind of clean-slate, fully optimized flash drive approach?"

So far, the Solid State Disk crowd has been thinking totally IN the box...the box made, defined, interfaced, prescribed by nearly 30 years of HDD-in-PC experience, from the time of the PC-XT in the early 1980s: a pure scaled-down IBM System mainframe memory subsystems...MPU-L1-L2-(L3)-DRAM-Disk-(DVD backup). The form factor and interface of SSDs, so far, is to make them drop-in compatible for HDDs, without disrupting the existing system architecture. Surely, the industry can do better than that, given the power and promise of raw NAND Flash's truly disruptive technologies.

For a while, it looked like the netbook might be the breakaway from HDD, with something of a clean slate on which to draw hardware and system software from the ground up. But though the market is exciting and fast growing, it has not embraced the SSD in a significant or innovative way. In fact, HDDs hold the high ground in the current crop of netbooks, though we are still a long way from the finish line, as varieties of small "computers" proliferate. So, what form of storage will be adopted in this part of the market it is not a settled issue.

Still, for the broad masses of laptops and desktop PCs, a complete SSD solution is probably not within reach any time soon (like, by 2013 or so), though undoubtedly, they will be picked up by early adopters, and those with special workload requirements. Much of the early enthusiasm, and many of the agressive penetration forecasts have been tempered by time, and by the hard market realities.

But, all is not lost, by any means.

Flash Caches are again in the news: Perhaps a more promising approach is a recurrence of flash-caching, in which a smaller SSD (a booster 'flash array', or HDD cache) with good software, can come close to the performance of a full solid state drive, but with the bulk of the system GB still on the HDD, at far lower cost (or 'average cost/GB') for the total system. This concept first appeared years ago in the early days of SSD-talk, but was quickly dismissed in the clamor to go directly to SSDs. Development, more discussion and market, technical and pricing realities for all competitive products have resurrected talk of HDD caching methods and systems. Today, we understand better, we have better flash-cache products, better hardware and software, and we see the naivete of thinking NAND flash would catch and surpass HDD in overall system cost, for the capacities widely in use in computer hard drives.